memoro

Name: memoro
Author: circassian1977-byte

Local

github.com/circassian1977-byteMemory & Knowledge0Updated 5d ago

Repository

About memoro

Memoro is a Windows app that keeps topic-based memory cards on a user's computer for AI assistants to read and update across chats. It connects through MCP and can optionally bridge browser and phone AI services through the user's Cloudflare account.

Key features

01Topic-based status cards
02Memory stored on the local PC
03Older card versions retained
04MCP access for connected AI assistants
05Optional Cloudflare bridge

Use cases

01Continue a project across different AI chats
02Share decisions and next steps among connected assistants
03Keep durable AI memory on a personal computer

MCP support

Memoro runs locally and exposes memory to AI assistants through MCP tools. Claude Desktop connects locally; browser and phone services can use an optional bridge deployed to the user's Cloudflare account.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config

{
  "mcpServers": {
    "circassian1977-byte-memoro": {
      "command": "npx",
      "args": [
        "-y",
        "@memoro/mcp-server"
      ]
    }
  }
}

Run commandnpx -y @memoro/mcp-server

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages

npm@memoro/mcp-server1.0.0stdio

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

Memoro: Long-Term Memory for AI

Your AI forgets. Memoro remembers — in every chat, across every AI.

🌐 Website: getmemoro.pages.dev · Türkçe · Русский

Memoro is a Windows app that gives your AI a long-term memory: every new chat — in Claude, ChatGPT, Grok or Perplexity — picks up where you left off instead of starting from zero. Explain your project once; every AI you connect reads and updates the same short "status cards", so you stop re-explaining context every time you switch tools.

Why

Every AI chat starts from zero. Plan with Claude on Monday, continue in ChatGPT on Tuesday, and you spend the first ten minutes re-explaining everything. Built-in AI memories are locked inside a single app and don't talk to each other. Memoro is one memory for all of them — without sending your data to a server we run (we don't run one).

How it works

Memoro runs quietly in the background on your PC and exposes your memory to AI assistants through MCP (Model Context Protocol).
Memory is kept as status cards: one focused, up-to-date summary per topic (what was decided, what was ruled out, what's next). Cards are updated instead of piling up contradictions, and older versions are kept.
Claude Desktop connects locally. Browser and phone AIs (claude.ai, ChatGPT, Grok, Perplexity) connect through an optional bridge that Memoro deploys to your own free Cloudflare account.
Memoro does not scrape your chats. The AI writes cards through Memoro's tools when something is worth keeping, or when you ask.

Free and Pro

	Free	Pro — $39.99/year or $4.99/month
Claude Desktop connection	✓	✓
Unlimited memories and status cards	✓	✓
claude.ai, ChatGPT, Grok, Perplexity	—	✓
Phone and browser access (cloud bridge)	—	✓
"Add AI" for any MCP-compatible assistant	—	✓
Sync across several PCs	—	✓
Team Projects (beta)	—	✓

Every new install gets all Pro features free for 7 days, no card required. To activate Pro, paste the license key from your purchase email into the License section of the Memoro control panel.

Download

Windows 10 / 11 — get Memoro from the Microsoft Store (free). Everything it needs is included, Windows installs it without warnings, and updates arrive automatically through the Store. Mac and Linux are planned.

Release notes

Privacy

Your memory lives on your computer (and, if you enable it, in your own Cloudflare account). No account with us, no ads, no tracking, no data sales. Full policy: getmemoro.pages.dev/privacy.

Status and feedback

Early stage, actively developed. Questions and bug reports: open an issue.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

Read the getting-started guide

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.